library(phyloseq) # for phyloseq object
library(ggplot2)
library(cowplot)
library(plyr)
library(dplyr)
library("plotly") # plot 3D
library("microbiome") # for centered log-ratio
library("coda") # Aitchison distance
library("coda.base") # Aitchison distance
library("vegan") # NMDS
library(pheatmap) # for heatmap
# Set path
path <- "~/Projects/IBS_Meta-analysis_16S"
# Import phyloseq object
physeq.mars <- readRDS(file.path(path, "phyloseq-objects/physeq_mars.rds"))
physeq.mars <- prune_samples(sample_sums(physeq.mars)>=500, physeq.mars)
# Sanity check
physeq.mars
## phyloseq-class experiment-level object
## otu_table() OTU Table: [ 1561 taxa and 69 samples ]
## sample_data() Sample Data: [ 69 samples by 12 sample variables ]
## tax_table() Taxonomy Table: [ 1561 taxa by 7 taxonomic ranks ]
Phylogenetic tree was computed with the package phangorn, and the script was run on a cluster. Let’s check we have correctly generated a phylogenetic tree.
# Look at the tree
plot_tree(physeq.mars, color = "host_disease", ladderize="left")
# Plot Phylum
plot_bar(physeq.mars, fill = "Phylum") + facet_wrap("host_disease", scales="free") +
theme(axis.text.x = element_text(size = 8))+
labs(x = "Samples", y = "Absolute abundance", title = "Mars dataset (2020)")
# Plot Class
plot_bar(physeq.mars, fill = "Class")+ facet_wrap("host_disease", scales="free") +
theme(axis.text.x = element_text(size = 8))+
labs(x = "Samples", y = "Absolute abundance", title = "Mars dataset (2020)")
Sequencing depth characteristics of the Mars dataset:
- minimum of 1140 total count per sample
- median: 3.255610^{4} total count per sample
- maximum of 6.360210^{4} total count per sample
# Agglomerate to phylum & class levels
phylum.table <- physeq.mars %>%
tax_glom(taxrank = "Phylum") %>% # agglomerate at phylum level
transform_sample_counts(function(x) {x/sum(x)} ) %>% # Transform to rel. abundance
psmelt() # Melt to long format
class.table <- physeq.mars %>%
tax_glom(taxrank = "Class") %>%
transform_sample_counts(function(x) {x/sum(x)} ) %>%
psmelt()
# Plot relative abundances
ggplot(phylum.table, aes(x = Sample, y = Abundance, fill = Phylum))+
facet_wrap(~ host_disease, scales = "free") + # scales = "free" removes empty lines
geom_bar(stat = "identity") +
theme(axis.text.x = element_text(size = 8, angle = -90))+
labs(x = "Samples", y = "Relative abundance", title = "Mars dataset (2020)")
ggplot(class.table, aes(x = Sample, y = Abundance, fill = Class))+
facet_wrap(~ host_disease, scales = "free") + # scales = "free" removes empty lines
geom_bar(stat = "identity") +
theme(axis.text.x = element_text(size = 8, angle = -90))+
labs(x = "Samples", y = "Relative abundance", title = "Mars dataset (2020)")
# Extract abundance of only Bacteroidota and Firmicutes
bacter <- phylum.table %>%
filter(Phylum == "Bacteroidota") %>%
select(c('Sample', 'Abundance', 'host_disease', 'Phylum', 'host_subtype', 'Collection')) %>%
arrange(Sample)
firmi <- phylum.table %>%
filter(Phylum == "Firmicutes") %>%
select(c('Sample', 'Abundance', 'host_disease', 'Phylum', 'host_subtype', 'Collection')) %>%
arrange(Sample)
# Calculate log2 ratio Firmicutes/Bacteroidota
ratio.FB <- data.frame('Sample' = bacter$Sample,
'host_disease' = bacter$host_disease,
'host_subtype' = bacter$host_subtype,
'Collection' = bacter$Collection,
'Bacteroidota' = bacter$Abundance,
'Firmicutes' = firmi$Abundance)
ratio.FB$logRatioFB <- log2(ratio.FB$Firmicutes / ratio.FB$Bacteroidota)
# Plot log2 ratio Firmicutes/Bacteroidota
ggplot(ratio.FB, aes(x = host_disease, y = logRatioFB))+
geom_boxplot(outlier.shape = NA)+
geom_jitter(width=0.1)+
labs(x = "", y = 'Log2(Firmicutes/Bacteroidota)', title = "Firmicutes:Bacteroidota ratio")+
theme_cowplot()
# Plot by IBS subtype
ggplot(ratio.FB, aes(x = host_subtype, y = logRatioFB))+
geom_boxplot(outlier.shape = NA)+
geom_jitter(width=0.1)+
labs(x = "", y = 'Log2(Firmicutes/Bacteroidota)', title = "Firmicutes:Bacteroidota ratio")+
theme_cowplot()
# Plot by IBS subtype with collection time 1 or 2
ggplot(ratio.FB, aes(x = host_subtype, y = logRatioFB))+
geom_boxplot(outlier.shape = NA)+
geom_jitter(width=0.1)+
facet_wrap(~Collection)+
labs(x = "", y = 'Log2(Firmicutes/Bacteroidota)', title = "Firmicutes:Bacteroidota ratio")+
theme_cowplot()+
theme(axis.text.x = element_text(angle=90))
# Sanity check no sample with less than 500 total count
table(sample_sums(physeq.mars)<500) # all FALSE
#____________________________________________________________________
# PHYLOSEQ OBJECT WITH NON-ZERO COMPOSITIONS
physeq.NZcomp <- physeq.mars
otu_table(physeq.NZcomp)[otu_table(physeq.NZcomp) == 0] <- 0.5 # pseudocounts
# Sanity check that 0 values have been replaced
# otu_table(physeq.mars)[1:5,1:5]
# otu_table(physeq.NZcomp)[1:5,1:5]
# transform into compositions
physeq.NZcomp <- transform_sample_counts(physeq.NZcomp, function(x) x / sum(x) )
table(rowSums(otu_table(physeq.NZcomp))) # check if there is any row not summing to 1
# Save object
saveRDS(physeq.NZcomp, file.path(path, "data/analysis-individual/Mars-2020/02_EDA-Mars/physeq_NZcomp.rds"))
#____________________________________________________________________
# PHYLOSEQ OBJECT WITH RELATIVE COUNT (BETWEEN 0 AND 1)
physeq.rel <- physeq.mars
physeq.rel <- transform_sample_counts(physeq.rel, function(x) x / sum(x) ) # divide each count by the total number of counts (per sample)
# check the counts are all relative
# otu_table(physeq.mars)[1:5, 1:5]
# otu_table(physeq.rel)[1:5, 1:5]
# sanity check
table(rowSums(otu_table(physeq.rel))) # check if there is any row not summing to 1
# save the physeq.rel object
saveRDS(physeq.rel, file.path(path, "data/analysis-individual/Mars-2020/02_EDA-Mars/physeq_relative.rds"))
#____________________________________________________________________
# PHYLOSEQ OBJECT WITH COMMON-SCALE NORMALIZATION
physeq.CSN <- physeq.mars
physeq.CSN <- transform_sample_counts(physeq.CSN, function(x) (x*min(sample_sums(physeq.CSN))) / sum(x) )
# sanity check
table(rowSums(otu_table(physeq.CSN))) # check that all rows are summing to the same total
# save the physeq.CSN object
saveRDS(physeq.CSN, file.path(path, "data/analysis-individual/Mars-2020/02_EDA-Mars/physeq_CSN.rds"))
#____________________________________________________________________
# PHYLOSEQ OBJECT WITH CENTERED LOG RATIO COUNT
physeq.clr <- physeq.mars
physeq.clr <- microbiome::transform(physeq.mars, "clr") # the function adds pseudocounts itself
# Compare the otu tables in the original phyloseq object and the new one after CLR transformation
otu_table(physeq.mars)[1:5, 1:5] # should contain absolute counts
otu_table(physeq.clr)[1:5, 1:5] # should all be relative
# save the physeq.rel object
saveRDS(physeq.clr, file.path(path, "data/analysis-individual/Mars-2020/02_EDA-Mars/physeq_clr.rds"))
First, let’s look at these four distances of interest.
#____________________________________________________________________________________
# Measure distances
getDistances <- function(){
# set.seed(123) # for unifrac, need to set a seed
# glom.UniF <- UniFrac(physeq.rel, weighted=TRUE, normalized=TRUE) # weighted unifrac
glom.ait <- phyloseq::distance(physeq.clr, method = 'euclidean') # aitchison
glom.bray <- phyloseq::distance(physeq.CSN, method = "bray") # bray-curtis
glom.can <- phyloseq::distance(physeq.NZcomp, method = "canberra") # canberra
dist.list <- list(#"UniF" = glom.UniF,
"Ait" = glom.ait, "Canb" = glom.can, "Bray" = glom.bray)
return(dist.list)
}
#____________________________________________________________________________________
# Plot in 2D the distances
plotDistances2D <- function(dlist, ordination="MDS"){
plist <- NULL
# plist <- vector("list", 4)
# names(plist) <- c("Weighted Unifrac", "Aitchison", "Bray-Curtis", "Canberra")
plist <- vector("list", 3)
names(plist) <- c("Aitchison", "Bray-Curtis", "Canberra")
# print("Unifrac")
# # Weighted UniFrac
# set.seed(123)
# iMDS.UniF <- ordinate(physeq.rel, ordination, distance=dlist$UniF)
# plist[[1]] <- plot_ordination(physeq.rel, iMDS.UniF, color="host_disease")
print("Aitchison")
# Aitchison
set.seed(123)
iMDS.Ait <- ordinate(physeq.clr, ordination, distance=dlist$Ait)
plist[[1]] <- plot_ordination(physeq.clr, iMDS.Ait, color="host_disease")
print("Bray")
# Bray-Curtis
set.seed(123)
iMDS.Bray <- ordinate(physeq.CSN, ordination, distance=dlist$Bray)
plist[[2]] <- plot_ordination(physeq.CSN, iMDS.Bray, color="host_disease")
print("Canberra")
# Canberra
set.seed(123)
iMDS.Can <- ordinate(physeq.NZcomp, ordination, distance=dlist$Can)
plist[[3]] <- plot_ordination(physeq.NZcomp, iMDS.Can, color="host_disease")
# Creating a dataframe to plot everything
plot.df = ldply(plist, function(x) x$data)
names(plot.df)[1] <- "distance"
return(plot.df)
}
Now let’s plot!
# Get the distances & the plot data
dist.mars <- getDistances()
plot.df <- plotDistances2D(dist.mars)
## [1] "Aitchison"
## [1] "Bray"
## [1] "Canberra"
# Plot
ggplot(plot.df, aes(Axis.1, Axis.2, color=host_disease))+
geom_point(size=6, alpha=0.5) + scale_color_manual(values = c('blue', 'red'))+
facet_wrap(distance~., scales='free', nrow=1)+
theme_bw()+
theme(strip.text.x = element_text(size=20))+
labs(color="Disease")
# ggsave(file.path(path.plots, "distances4_MDS.jpg"), height = 4, width = 15)
# ggsave(file.path(path.plots, "distances4_MDS.jpg"), height = 4, width = 10)
For better visualization, we will also take a glance at reduction to 3D.
#____________________________________________________________________________________
# Plot 3D ordination
plotDistances3D <- function(d, name_dist){
# Reset parameters
mds.3D <- NULL
xyz <- NULL
fig.3D <- NULL
# Reduce distance matrix to 3 dimensions
set.seed(123)
mds.3D <- metaMDS(d, method="MDS", k=3, trace = 0)
xyz <- scores(mds.3D, display="sites") # pull out the (x,y,z) coordinates
# Plot
fig.3D <- plot_ly(x=xyz[,1], y=xyz[,2], z=xyz[,3], type="scatter3d", mode="markers",
color=sample_data(physeq.mars)$host_disease, colors = c("blue", "red"))%>%
layout(title = paste('MDS in 3D with', name_dist, 'distance', sep = ' '))
return(fig.3D)
}
Now let’s plot!
# plotDistances3D(dist.mars$UniF, "UniFrac")
plotDistances3D(dist.mars$Ait, "Aitchison")
plotDistances3D(dist.mars$Canb, "Canberra")
plotDistances3D(dist.mars$Bray, "Bray-Curtis")
# For heatmaps: have group color
matcol <- data.frame(group = sample_data(physeq.mars)[,"host_disease"])
# Function to get heatmap from the distances computed
plotHeatmaps <- function(dlist, fontsize){
# Initialize variables
i=1
# plist <- vector("list", 4)
plist <- vector("list", 3)
names(plist) <- names(dlist)
# Loop through distances
for(d in dlist){
plist[[i]] <- pheatmap(as.matrix(d),
clustering_distance_rows = d,
clustering_distance_cols = d,
fontsize = fontsize,
fontsize_col = fontsize-5,
fontsize_row = fontsize-5,
annotation_col = matcol,
annotation_row = matcol,
annotation_colors = list(host_disease = c('Healthy' = 'blue', 'IBS' = 'red')),
cluster_rows = T,
cluster_cols = T,
clustering_method = 'complete', # hc method
main = names(dlist)[i]) # have name of distance as title
i <- i+1
}
return(plist)
}
# Get the heatmaps
heatmp.mars <- plotHeatmaps(dlist = dist.mars, fontsize = 8)